| { | |
| "best_metric": 0.4796141982078552, | |
| "best_model_checkpoint": "/content/output_dir/checkpoint-268", | |
| "epoch": 10.0, | |
| "global_step": 2680, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4796141982078552, | |
| "eval_matthews_correlation": 0.5351033849356494, | |
| "eval_runtime": 8.8067, | |
| "eval_samples_per_second": 118.433, | |
| "eval_steps_per_second": 14.875, | |
| "step": 268, | |
| "learning_rate": 1.8067415730337083e-05, | |
| "loss": 0.4913 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5334435701370239, | |
| "eval_matthews_correlation": 0.5178799252679331, | |
| "eval_runtime": 8.9439, | |
| "eval_samples_per_second": 116.616, | |
| "eval_steps_per_second": 14.647, | |
| "step": 536, | |
| "learning_rate": 1.605992509363296e-05, | |
| "loss": 0.2872 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5544090270996094, | |
| "eval_matthews_correlation": 0.5649788851042796, | |
| "eval_runtime": 8.9467, | |
| "eval_samples_per_second": 116.58, | |
| "eval_steps_per_second": 14.642, | |
| "step": 804, | |
| "learning_rate": 1.4052434456928841e-05, | |
| "loss": 0.1777 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.5754779577255249, | |
| "eval_matthews_correlation": 0.6105374636148787, | |
| "eval_runtime": 8.8982, | |
| "eval_samples_per_second": 117.215, | |
| "eval_steps_per_second": 14.722, | |
| "step": 1072, | |
| "learning_rate": 1.2044943820224718e-05, | |
| "loss": 0.1263 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.7263916730880737, | |
| "eval_matthews_correlation": 0.5807606001872874, | |
| "eval_runtime": 8.9705, | |
| "eval_samples_per_second": 116.27, | |
| "eval_steps_per_second": 14.603, | |
| "step": 1340, | |
| "learning_rate": 1.0037453183520601e-05, | |
| "loss": 0.0905 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.8121512532234192, | |
| "eval_matthews_correlation": 0.5651092792103851, | |
| "eval_runtime": 8.9924, | |
| "eval_samples_per_second": 115.987, | |
| "eval_steps_per_second": 14.568, | |
| "step": 1608, | |
| "learning_rate": 8.02996254681648e-06, | |
| "loss": 0.0692 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.941014289855957, | |
| "eval_matthews_correlation": 0.5632084517291658, | |
| "eval_runtime": 8.9583, | |
| "eval_samples_per_second": 116.428, | |
| "eval_steps_per_second": 14.623, | |
| "step": 1876, | |
| "learning_rate": 6.022471910112359e-06, | |
| "loss": 0.0413 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0095174312591553, | |
| "eval_matthews_correlation": 0.5856531698367675, | |
| "eval_runtime": 9.0029, | |
| "eval_samples_per_second": 115.851, | |
| "eval_steps_per_second": 14.551, | |
| "step": 2144, | |
| "learning_rate": 4.01498127340824e-06, | |
| "loss": 0.0327 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.0425965785980225, | |
| "eval_matthews_correlation": 0.5941395545037332, | |
| "eval_runtime": 8.9217, | |
| "eval_samples_per_second": 116.906, | |
| "eval_steps_per_second": 14.683, | |
| "step": 2412, | |
| "learning_rate": 2.00749063670412e-06, | |
| "loss": 0.0202 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.0782166719436646, | |
| "eval_matthews_correlation": 0.5956649094312695, | |
| "eval_runtime": 8.9472, | |
| "eval_samples_per_second": 116.572, | |
| "eval_steps_per_second": 14.641, | |
| "step": 2680, | |
| "learning_rate": 0.0, | |
| "loss": 0.0104 | |
| } | |
| ], | |
| "max_steps": 2680, | |
| "num_train_epochs": 10, | |
| "total_flos": 7113018526540800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |